Digital behavioural traces have become an important source of evidence for studying population behaviour, especially as social, economic, and informational activities increasingly take place online. Web-tracking data have been particularly valuable because they capture high-frequency signals of how individuals search, navigate, compare sources, and interact with digital environments. However, this empirical foundation is being disrupted by the rapid diffusion of artificial intelligence (AI) technologies, especially large language models (LLMs), which increasingly redirect user behaviour from exploring different information sources online to requesting direct answers within chats embedded in closed platforms. This paper discusses the methodological foundations of using web-tracking data for demographic inference and examines how these data are combined with surveys, censuses, and administrative records. It then analyses how the shift from browsing to AI prompting may reduce the observability, richness, and comparability of digital behavioural traces. By assessing both the opportunities and limitations of these data, the article clarifies their role in demographic research and considers how computational social science and evidence-based social policy may need to adapt in an increasingly AI-mediated information environment.
Offline reinforcement learning (RL) has emerged as a promising paradigm for robotic skill acquisition, particularly for manipulation tasks where real-world trial-and-error interaction is costly, time-consuming, or unsafe. In contrast to broad offline RL surveys, this paper presents a focused narrative review centered on robotic manipulation under data-limited conditions, where datasets often suffer from narrow state–action coverage, sparse successful demonstrations, noisy trajectories, and limited behavioral diversity. These constraints exacerbate key challenges in offline RL, including distributional shift, unstable value estimation, weak reward propagation under sparsity, and poor policy generalization. This paper adopts a focused narrative review methodology; it does not claim systematic review status and does not follow a PRISMA protocol, but instead provides a structured, evidence-informed synthesis of representative offline RL methods selected for their methodological significance, benchmark relevance, and applicability to data-limited robotic manipulation conditions. The review analyzes major families of offline RL methods, including conservative value-based approaches, behavior-constrained learning, advantage-weighted methods, uncertainty-aware techniques, model-based offline RL, sequence-modeling approaches, and offline-to-online adaptation strategies. The discussion is grounded in benchmark observations from D4RL and NeoRL, alongside evidence from robotic manipulation systems such as QT-Opt and RoboNet. Comparative analysis suggests that conservative and uncertainty-aware methods typically offer stronger robustness and policy stability under constrained robotic datasets, whereas behavior-constrained and advantage-based approaches remain highly sensitive to dataset quality, behavioral diversity, and reward structure. Model-based and sequence-modeling methods can further improve data efficiency and long-horizon capability, but introduce additional challenges related to model reliability, synthetic rollout fidelity, and sequential data requirements. The paper also discusses practical issues in real-world deployment, including safety constraints, contact instability, sensor noise, and safe online adaptation. Finally, it highlights future research directions such as uncertainty-aware learning, physics-informed world models, foundation models, representation learning, and safe offline-to-online adaptation for robotic manipulation. Overall, this review provides a targeted synthesis of offline RL methods for robotic manipulation under realistic data-scarce conditions, while identifying key limitations, benchmark trends, and open research challenges for next-generation robotic learning systems.
Several studies have recently recommended the Matthews correlation coefficient (MCC) to evaluate the accuracy of hard classifications. However, because it is derived from the Pearson correlation, it contains properties that may not be appropriate for classification metrics, such as the value of 0 indicating a lack of relationship. The scaled Brier score was originally conceived for continuous probabilities but may overcome these limitations, such as a value of 0 indicating a random association (i.e., no better than predicting the sample prevalence for each observation). We evaluated the impact of prevalence on the scaled Brier score versus MCC and other common performance metrics with simulated binary and multiclass data. Scenarios with varying sensitivity, specificity, positive predictive value, and prevalence were generated. The following performance metrics were evaluated: accuracy, balanced accuracy, Brier and scaled Brier scores, F score, Kappa and prevalence-adjusted and bias-adjusted Kappa statistics, MCC, receiver operating characteristic and precision-recall area under the curves, and Youden Index. Three prevalence-related criteria were proposed and used to evaluate performance metrics: metric values should not be identical with changes in prevalence; metric values should decrease when prevalence increases and only non-cases are predicted; and metric values should increase when prevalence increases and only cases are predicted. Only the scaled Brier score satisfied all three proposed criteria, but accuracy, 1 - Brier score, and PABAK satisfied the first criterion and partially satisfied the second and third criteria. The scaled Brier score consistently reported the lowest values and often deviated substantially from other performance metrics. The scaled Brier score was the most consistent with the proposed criteria for binary and multiclass data based on this analysis. The scaled Brier score reported lower values than other performance metrics in all cases and the differences were often large enough to generate substantially different conclusions. The scaled Brier score has previously been recommended as a measure of predictive accuracy for continuous probabilities and the current study indicates that this recommendation can be extended to hard classification data.
Abstract Transaction fraud detection remains difficult because fraudulent events are highly imbalanced, temporally drifting, cost asymmetric, and often supported by limited auditability in model decisions. Existing tabular, tree-based, and deep fraud detectors can achieve strong predictive performance, but they often provide weak verifier-grounded reasoning, incomplete probability calibration, and limited integration with cost-sensitive decisioning. This paper proposes TEMPLAR-Fraud, a verifier-grounded, calibrated, and cost-sensitive framework for transaction fraud detection. The framework combines SAINT-based transaction representation learning, CatBoost triage, routed symbolic template reasoning, deterministic rationale verification, Bayesian stacking, one-dimensional optimal transport calibration, and validation-selected cost-sensitive thresholding. Evaluation was conducted on BAF Base and IEEE-CIS Fraud Detection using chronological train/validation/test splits, internal testing, same-dataset temporal future-slice evaluation, calibration analysis, cost-sensitive utility assessment, robustness testing, adversarial stress testing, computational-efficiency measurement, and explanation-safety analysis. On the internal chronological test sets, TEMPLAR-Fraud achieved AUROC/AUC-PR/F1 scores of 0.918/0.498/0.557 on BAF Base and 0.972/0.701/0.747 on IEEE-CIS Fraud Detection. Under same-dataset temporal future-slice evaluation, it retained AUROC/AUC-PR/F1 scores of 0.901/0.452/0.518 and 0.951/0.642/0.687, while reducing ECE after calibration to 0.014 and 0.013 and producing the highest reported net savings under the stated experimental cost model. These findings suggest that framework-level integration of routed prediction, verified rationale generation, calibration, and cost-sensitive thresholding can improve fraud-detection evaluation under controlled benchmark protocols.
Cybercrime research in Nigeria has largely focused on offender motivations, victim experiences, and regulatory gaps, with limited use of official administrative data to examine the institutional structure of cybercrime enforcement. This study provides a systematic analysis of cyber-related convictions recorded by the Economic and Financial Crimes Commission (EFCC) in 2022. Using a keyword-based content analysis of publicly available EFCC conviction records (N = 3785), the study identifies and classifies cyber-enabled offences and develops an institutional typology of prosecuted cybercrime in Nigeria. A total of 524 cyber-related cases were extracted from the full conviction dataset and grouped into analytic offence categories. These categories were inductively derived from the offence descriptions recorded in the dataset and include: impersonation and identity fraud; cybercrime and affiliated offences (general); computer-related offences; and business email compromise. Descriptive statistical analysis was used to examine the distribution of offence types and to assess patterns in enforcement focus. Findings indicate that Nigerian cybercrime enforcement is heavily concentrated on impersonation-based and cyber-affiliated offences, with relatively limited representation of technically driven cyber offences. The study demonstrates how institutional data can be used to generate empirical insights into national cybercrime profiles and highlights structural concentration in enforcement priorities. The results contribute to cybercrime scholarship by shifting attention from perception-based studies toward evidence derived from formal criminal justice records. Importantly, the study’s scope is limited to EFCC conviction records, and its findings reflect the enforcement priorities of this specific agency rather than the full landscape of cybercrime prosecution in Nigeria.
